Machine learning modeling using social graph signals
Systems and methods are provided for receiving a request for lookalike data, the request for lookalike data comprising seed data and generating sample data from the seed data and from user data for a plurality of users, to use in a lookalike model training. The systems and methods further provide for capturing a snapshot of social graph data for a plurality of users and computing social graph features based on the seed data and the user data for the plurality of users, training a lookalike model based on the sample data and the computed social graph features to generate a trained lookalike model, generating a lookalike score for each user of the plurality of users in the user data using the trained lookalike model, and generating a list comprising a unique identifier for each user of the plurality of users and an associated lookalike score for each unique identifier.
1. A method comprising:
receiving, at a server computer system, a request for lookalike data, the request for lookalike data comprising seed data;
generating, by the server computer system, sample data from the seed data and from user data for a plurality of users, to use in a lookalike model training, by performing operations comprising:
generating a positive data sample from the seed data to use in the lookalike model training; and
generating a negative data sample from user data stored in a database to use in the lookalike model training;
capturing, by the server computer system, a snapshot of social graph data for the plurality of users and computing social graph features based on the seed data and the user data for the plurality of users;
training, by the server computer system, a lookalike model based on the sample data, user profile features for the plurality of users, and the computed social graph features to generate a trained lookalike model;
generating, by the server computer system, a lookalike score for each user of the plurality of users in the user data using the trained lookalike model; and
generating, by the server computer system, a list comprising a unique identifier for each user of the plurality of users and an associated lookalike score for each unique identifier.
2. The method of claim 1 , wherein the positive data sample comprises the seed data.
3. The method of claim 1 , wherein the negative data sample comprises a subset of the user data for the plurality of users.
4. The method of claim 1 , further comprising:
capturing a user profile snapshot;
generating user profile feature data; and
storing the user profile feature data.
5. The method of claim 1 , wherein the request further comprises filter characteristics, and the method further comprises:
filtering the list comprising each user and an associated lookalike score for each user, based on the filter characteristics received in the request; and
associating the filtered list with the request.
6. The method of claim 1 , wherein the seed data comprises a plurality of user identifiers.
7. The method of claim 1 , wherein the generated list comprising a unique identifier for each user of the plurality of users, and an associated lookalike score for each unique identifier, is of a size indicated by the request for the lookalike data.
8. The method of claim 1 , wherein the plurality of users are users of a messaging system or social networking system.
9. The method of claim 1 , wherein the generated list is associated with a requester that sent the request for the lookalike data, and the method further comprises:
receiving content from the requester; and
displaying the content to one or more users of the plurality of users, based on the generated list.
10. A server computer comprising:
one or more hardware processors; and
a computer-readable medium coupled with the one or more hardware processors, the computer-readable medium comprising instructions stored thereon that are executable by the one or more hardware processors to cause the server computer to perform operations comprising:
receiving a request for lookalike data, the request for lookalike data comprising seed data;
generating sample data from the seed data and from user data for a plurality of users, to use in a lookalike model training, by performing operations comprising:
generating a positive data sample from the seed data to use in the lookalike model training; and
generating a negative data sample from user data stored in a database to use in the lookalike model training;
capturing a snapshot of social graph data for the plurality of users and computing social graph features based on the seed data and the user data for the plurality of users;
training a lookalike model based on the sample data, user profile features for the plurality of users, and the computed social graph features to generate a trained lookalike model;
generating a lookalike score for each user of the plurality of users in the user data using the trained lookalike model; and
generating a list comprising a unique identifier for each user of the plurality of users and an associated lookalike score for each unique identifier.
11. The server computer of claim 10 , wherein the positive data sample comprises the seed data.
12. The server computer of claim 10 , wherein the negative data sample comprises a subset of the user data for the plurality of users.
13. The server computer of claim 10 , the operations further comprising:
capturing a user profile snapshot;
generating user profile feature data; and
storing the user profile feature data.
14. The server computer of claim 10 , wherein the request further comprises filter characteristics, and the operations further comprise:
filtering the list comprising each user and an associated lookalike score for each user, based on the filter characteristics received in the request; and
associating the filtered list with the request.
15. The server computer of claim 10 , wherein the generated list comprising a unique identifier for each user of the plurality of users, and an associated lookalike score for each unique identifier, is of a size indicated by the request for the lookalike data.
16. The server computer of claim 10 , wherein the plurality of users are users of a messaging system or social networking system.
17. The server computer of claim 10 , wherein the generated list is associated with a requester that sent the request for the lookalike data, and the operations further comprise:
receiving content from the requester; and
displaying the content to one or more users of the plurality of users, based on the generated list.
18. A non-transitory computer-readable medium comprising instructions stored thereon that are executable by at least one processor to cause a computing device to perform operations comprising:
receiving a request for lookalike data, the request for lookalike data comprising seed data;
generating sample data from the seed data and from user data for a plurality of users, to use in a lookalike model training, by performing operations comprising:
generating a positive data sample from the seed data to use in the lookalike model training; and
generating a negative data sample from user data stored in a database to use in the lookalike model training;
capturing a snapshot of social graph data for the plurality of users and computing social graph features based on the seed data and the user data for the plurality of users;
training a lookalike model based on the sample data, user profile features for the plurality of users, and the computed social graph features to generate a trained lookalike model;
generating a lookalike score for each user of the plurality of users in the user data using the trained lookalike model; and
generating a list comprising a unique identifier for each user of the plurality of users and an associated lookalike score for each unique identifier.
19. The non-transitory computer-readable medium of claim 18 , wherein the positive data sample comprises the seed data.
20. The non-transitory computer-readable medium of claim 18 , wherein the negative data sample comprises a subset of the user data for the plurality of users.